CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mcp-access

Open the GBrain owner dashboard, manage MCP clients and permissions, or connect a native OAuth harness. Distinguishes owner administration from ordinary MCP access.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugin-variants/gbrain-daily/skills/mcp-access/SKILL.md

The canonical home for this skill is mcp-access in garrytan/gbrain

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tightly written, information-dense administration skill: nearly every sentence carries domain-specific operational guidance, destructive operations have explicit preview-and-confirm checkpoints, and failure modes get concrete diagnosis and recovery paths. The main gaps are the absence of a single end-to-end worked sequence and an unverified relative reference to a conventions file outside the bundle.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational specifics (command flags, error-code semantics, failure-recovery rules) and contains essentially no padding or explanations of concepts Claude already knows, fitting the 'efficient, minor instances that could be trimmed' anchor. It misses 5 because a few passages are overloaded (the grant_blocked_operations and hidden_tool_content bullets) and the unknown-outcome-after-mutation guidance is repeated across two sections.

4 / 5

Actionability

Concrete, executable guidance throughout: exact subcommands and flags (login-link --oauth-request ID, setup ID --flow authorization-code, mcp grant NAME --client ID --if-version N --dry-run, delete ID --yes --if-version N, gbrain doctor check grant_new_ops_available) plus specific error-diagnosis paths (read grant_diagnosis from whoami, relay fix, confirm with whoami). Not 5 because there is no complete copy-paste worked example and some exact syntax is deferred to the external ADMIN.md.

4 / 5

Workflow Clarity

Risky operations carry explicit validate-then-apply loops: permissions changes preview with --dry-run before/after, end-access commands preview consequences by default before --yes --if-version N, a failed transport after a mutation triggers inspect-before-retry, and grant_blocked_operations fixes are confirmed with whoami — so the destructive-operation cap does not apply. It sits below 5 because no single end-to-end sequence is laid out: the register, setup, verify, and consent stages must be synthesized across sections.

4 / 5

Progressive Disclosure

Sections are well organized by workflow stage (Contract, Owner actions, Native OAuth connection, When it fails, Anti-Patterns, Output Format), and external references are one level deep and clearly signaled with their purpose stated (ADMIN.md for commands and the recovery table, hosted guide for client installation, DEPLOY.md for the running service, plus a raw fallback URL for remote loading). Not 5 because ../conventions/agent-operator-protocol.md has no corresponding file in the bundle, and the lengthy 'When it fails' detail is inlined rather than offloaded to a reference file.

4 / 5

Total

16

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description that names concrete owner-administration actions and explicitly distinguishes itself from ordinary MCP access skills. Its main weakness is that the description field alone answers 'what' but not 'when' — explicit trigger guidance lives in a separate when_to_use frontmatter field rather than in the description itself.

Suggestions

Append a 'Use when...' clause to the description field itself (e.g., 'Use when the user asks to open the MCP admin panel, manage or revoke MCP clients, or set up MCP OAuth for a hosted GBrain server') so the description self-containedly answers both what and when.

Include the action verbs users actually say — 'register', 'revoke', 'invalidate tokens', 'admin panel' — to broaden natural trigger coverage within the description.

Briefly enumerate the remaining managed operations (token invalidation, client revocation/deletion) to close the coverage gap in the action list.

DimensionReasoningScore

Specificity

The description names the domain and several concrete actions — "Open the GBrain owner dashboard, manage MCP clients and permissions, or connect a native OAuth harness" — matching the anchor for several specific actions with minor gaps. It falls short of 5 because coverage is not comprehensive: token invalidation, client revocation/deletion, and registration are managed by the skill but unmentioned.

4 / 5

Completeness

The 'what' is clear and concrete, but the description field itself contains no 'Use when...' clause or equivalent trigger guidance — "Distinguishes owner administration from ordinary MCP access" is a boundary statement, not usage timing — so completeness is capped at 3 per the rubric guideline. A separate when_to_use frontmatter field does carry explicit trigger phrases, but it sits outside the evaluated description field; scoring 4 would require the 'when' to be present in the description itself.

3 / 5

Trigger Term Quality

Good keyword coverage with natural domain terms ("owner dashboard", "manage MCP clients", "permissions", "OAuth"), matching the 'good coverage, a few natural terms missing' anchor. Not 5 because common user phrasings like "admin panel", "login link", "register", and "revoke" are absent from the description.

4 / 5

Distinctiveness Conflict Risk

The description explicitly carves out a niche — "Distinguishes owner administration from ordinary MCP access" — and anchors on the GBrain owner dashboard/MCP client management, giving it distinct triggers with minimal conflict risk against generic MCP-access skills. This clearly matches the top anchor rather than the 'minor overlap risk' anchor at 4.

5 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

garrytan/gbrain

Path

plugin-variants/gbrain-daily/skills/mcp-access/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.